© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7571
    Prev
    Next
    INDEX
    Explanations

    Python code

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on relatively informative content-bearing nouns (as opposed to common function words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {~
    0.71
    avil
    0.71
    ĥ
    0.70
    sensing
    0.68
    one
    0.68
    body
    0.67
    enroll
    0.65
    %(
    0.65
    avoid
    0.64
    affirm
    0.64
    POSITIVE LOGITS
     funcionalidades
    1.09
     prestaciones
    1.05
     proteínas
    1.03
     ligados
    1.00
     enormes
    0.98
     autoridades
    0.97
     diferenci
    0.97
     normas
    0.96
     desempeñ
    0.94
     elegantes
    0.94
    Activations Density 0.000%

    No Known Activations